@google-cloud/discoveryengine 1.9.0 → 1.11.0

package/build/protos/google/cloud/discoveryengine/v1beta/chunk.proto

@@ -0,0 +1,119 @@
+// Copyright 2024 Google LLC
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.discoveryengine.v1beta;
+
+import "google/api/field_behavior.proto";
+import "google/api/resource.proto";
+import "google/protobuf/struct.proto";
+
+option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1Beta";
+option go_package = "cloud.google.com/go/discoveryengine/apiv1beta/discoveryenginepb;discoveryenginepb";
+option java_multiple_files = true;
+option java_outer_classname = "ChunkProto";
+option java_package = "com.google.cloud.discoveryengine.v1beta";
+option objc_class_prefix = "DISCOVERYENGINE";
+option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1beta";
+option ruby_package = "Google::Cloud::DiscoveryEngine::V1beta";
+
+// Chunk captures all raw metadata information of items to be recommended or
+// searched in the chunk mode.
+message Chunk {
+  option (google.api.resource) = {
+    type: "discoveryengine.googleapis.com/Chunk"
+    pattern: "projects/{project}/locations/{location}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
+    pattern: "projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
+  };
+
+  // Document metadata contains the information of the document of the current
+  // chunk.
+  message DocumentMetadata {
+    // Uri of the document.
+    string uri = 1;
+
+    // Title of the document.
+    string title = 2;
+
+    // Data representation.
+    // The structured JSON data for the document. It should conform to the
+    // registered [Schema][google.cloud.discoveryengine.v1beta.Schema] or an
+    // `INVALID_ARGUMENT` error is thrown.
+    google.protobuf.Struct struct_data = 3;
+  }
+
+  // Page span of the chunk.
+  message PageSpan {
+    // The start page of the chunk.
+    int32 page_start = 1;
+
+    // The end page of the chunk.
+    int32 page_end = 2;
+  }
+
+  // Metadata of the current chunk. This field is only populated on
+  // [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
+  // API.
+  message ChunkMetadata {
+    // The previous chunks of the current chunk. The number is controlled by
+    // [SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks][google.cloud.discoveryengine.v1beta.SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks].
+    // This field is only populated on
+    // [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
+    // API.
+    repeated Chunk previous_chunks = 1;
+
+    // The next chunks of the current chunk. The number is controlled by
+    // [SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks][google.cloud.discoveryengine.v1beta.SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks].
+    // This field is only populated on
+    // [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
+    // API.
+    repeated Chunk next_chunks = 2;
+  }
+
+  // The full resource name of the chunk.
+  // Format:
+  // `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}/chunks/{chunk_id}`.
+  //
+  // This field must be a UTF-8 encoded string with a length limit of 1024
+  // characters.
+  string name = 1;
+
+  // Unique chunk ID of the current chunk.
+  string id = 2;
+
+  // Content is a string from a document (parsed content).
+  string content = 3;
+
+  // Output only. Represents the relevance score based on similarity.
+  // Higher score indicates higher chunk relevance.
+  // The score is in range [-1.0, 1.0].
+  // Only populated on [SearchService.SearchResponse][].
+  optional double relevance_score = 8
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Metadata of the document from the current chunk.
+  DocumentMetadata document_metadata = 5;
+
+  // Output only. This field is OUTPUT_ONLY.
+  // It contains derived data that are not in the original input document.
+  google.protobuf.Struct derived_struct_data = 4
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Page span of the chunk.
+  PageSpan page_span = 6;
+
+  // Output only. Metadata of the current chunk.
+  ChunkMetadata chunk_metadata = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+}

package/build/protos/google/cloud/discoveryengine/v1beta/common.proto

@@ -51,11 +51,6 @@ option (google.api.resource_definition) = {
   type: "healthcare.googleapis.com/FhirStore"
   pattern: "projects/{project}/locations/{location}/datasets/{dataset}/fhirStores/{fhir_store}"
 };
-option (google.api.resource_definition) = {
-  type: "discoveryengine.googleapis.com/Chunk"
-  pattern: "projects/{project}/locations/{location}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
-  pattern: "projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document}/chunks/{chunk}"
-};
 
 // The industry vertical associated with the
 // [DataStore][google.cloud.discoveryengine.v1beta.DataStore].

package/build/protos/google/cloud/discoveryengine/v1beta/conversational_search_service.proto

@@ -587,6 +587,12 @@ message AnswerQueryRequest {
       // If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
       string order_by = 4;
 
+      // Specifies the search result mode. If unspecified, the
+      // search result mode defaults to `DOCUMENTS`.
+      // See [parse and chunk
+      // documents](https://cloud.google.com/generative-ai-app-builder/docs/parse-chunk-documents)
+      SearchRequest.ContentSearchSpec.SearchResultMode search_result_mode = 5;
+
       // Specs defining dataStores to filter on in a search call and
       // configurations for those dataStores. This is only considered for
       // engines with multiple dataStores use case. For single dataStore within
@@ -793,8 +799,10 @@ message AnswerQueryRequest {
 // method.
 message AnswerQueryResponse {
   // Answer resource object.
-  // If [AnswerQueryRequest.StepSpec.max_step_count][] is greater than 1,
-  // use [Answer.name][google.cloud.discoveryengine.v1beta.Answer.name] to fetch
+  // If
+  // [AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec.max_rephrase_steps][google.cloud.discoveryengine.v1beta.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec.max_rephrase_steps]
+  // is greater than 1, use
+  // [Answer.name][google.cloud.discoveryengine.v1beta.Answer.name] to fetch
   // answer information using
   // [ConversationalSearchService.GetAnswer][google.cloud.discoveryengine.v1beta.ConversationalSearchService.GetAnswer]
   // API.

package/build/protos/google/cloud/discoveryengine/v1beta/document.proto

@@ -54,7 +54,7 @@ message Document {
 
       // The URI of the content. Only Cloud Storage URIs (e.g.
       // `gs://bucket-name/path/to/file`) are supported. The maximum file size
-      // is 2.5 MB for text-based formats, 100 MB for other formats.
+      // is 2.5 MB for text-based formats, 200 MB for other formats.
       string uri = 3;
     }
 

package/build/protos/google/cloud/discoveryengine/v1beta/document_processing_config.proto

@@ -41,6 +41,30 @@ message DocumentProcessingConfig {
     pattern: "projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/documentProcessingConfig"
   };
 
+  // Configuration for chunking config.
+  message ChunkingConfig {
+    // Configuration for the layout based chunking.
+    message LayoutBasedChunkingConfig {
+      // The token size limit for each chunk.
+      //
+      // Supported values: 100-500 (inclusive).
+      // Default value: 500.
+      int32 chunk_size = 1;
+
+      // Whether to include appending different levels of headings to chunks
+      // from the middle of the document to prevent context loss.
+      //
+      // Default value: False.
+      bool include_ancestor_headings = 2;
+    }
+
+    // Additional configs that defines the behavior of the chunking.
+    oneof chunk_mode {
+      // Configuration for the layout based chunking.
+      LayoutBasedChunkingConfig layout_based_chunking_config = 1;
+    }
+  }
+
   // Related configurations applied to a specific type of document parser.
   message ParsingConfig {
     // The digital parsing configurations for documents.
@@ -57,6 +81,9 @@ message DocumentProcessingConfig {
       bool use_native_text = 2;
     }
 
+    // The layout parsing configurations for documents.
+    message LayoutParsingConfig {}
+
     // Configs for document processing types.
     oneof type_dedicated_config {
       // Configurations applied to digital parser.
@@ -65,6 +92,9 @@ message DocumentProcessingConfig {
       // Configurations applied to OCR parser. Currently it only applies to
       // PDFs.
       OcrParsingConfig ocr_parsing_config = 2;
+
+      // Configurations applied to layout parser.
+      LayoutParsingConfig layout_parsing_config = 3;
     }
   }
 
@@ -73,6 +103,9 @@ message DocumentProcessingConfig {
   // `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
   string name = 1;
 
+  // Whether chunking mode is enabled.
+  ChunkingConfig chunking_config = 3;
+
   // Configurations for default Document parser.
   // If not specified, we will configure it as default DigitalParsingConfig, and
   // the default parsing config will be applied to all file types for Document
@@ -85,8 +118,10 @@ message DocumentProcessingConfig {
   // * `pdf`: Override parsing config for PDF files, either digital parsing, ocr
   // parsing or layout parsing is supported.
   // * `html`: Override parsing config for HTML files, only digital parsing and
-  // or layout parsing are supported.
+  // layout parsing are supported.
   // * `docx`: Override parsing config for DOCX files, only digital parsing and
-  // or layout parsing are supported.
+  // layout parsing are supported.
+  // * `pptx`: Override parsing config for PPTX files, only digital parsing and
+  // layout parsing are supported.
   map<string, ParsingConfig> parsing_config_overrides = 5;
 }

package/build/protos/google/cloud/discoveryengine/v1beta/evaluation.proto

@@ -0,0 +1,231 @@
+// Copyright 2024 Google LLC
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.discoveryengine.v1beta;
+
+import "google/api/field_behavior.proto";
+import "google/api/resource.proto";
+import "google/cloud/discoveryengine/v1beta/search_service.proto";
+import "google/protobuf/timestamp.proto";
+import "google/rpc/status.proto";
+
+option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1Beta";
+option go_package = "cloud.google.com/go/discoveryengine/apiv1beta/discoveryenginepb;discoveryenginepb";
+option java_multiple_files = true;
+option java_outer_classname = "EvaluationProto";
+option java_package = "com.google.cloud.discoveryengine.v1beta";
+option objc_class_prefix = "DISCOVERYENGINE";
+option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1beta";
+option ruby_package = "Google::Cloud::DiscoveryEngine::V1beta";
+
+// An evaluation is a single execution (or run) of an evaluation process. It
+// encapsulates the state of the evaluation and the resulting data.
+message Evaluation {
+  option (google.api.resource) = {
+    type: "discoveryengine.googleapis.com/Evaluation"
+    pattern: "projects/{project}/locations/{location}/evaluations/{evaluation}"
+  };
+
+  // Describes the specification of the evaluation.
+  message EvaluationSpec {
+    // Describes the specification of the query set.
+    message QuerySetSpec {
+      // Required. The full resource name of the
+      // [SampleQuerySet][google.cloud.discoveryengine.v1beta.SampleQuerySet]
+      // used for the evaluation, in the format of
+      // `projects/{project}/locations/{location}/sampleQuerySets/{sampleQuerySet}`.
+      string sample_query_set = 1 [
+        (google.api.field_behavior) = REQUIRED,
+        (google.api.resource_reference) = {
+          type: "discoveryengine.googleapis.com/SampleQuerySet"
+        }
+      ];
+    }
+
+    // The search specification.
+    oneof search_spec {
+      // Required. The search request that is used to perform the evaluation.
+      //
+      // Only the following fields within SearchRequest are supported; if any
+      // other fields are provided, an UNSUPPORTED error will be returned:
+      //
+      // * [SearchRequest.serving_config][google.cloud.discoveryengine.v1beta.SearchRequest.serving_config]
+      // * [SearchRequest.branch][google.cloud.discoveryengine.v1beta.SearchRequest.branch]
+      // * [SearchRequest.canonical_filter][google.cloud.discoveryengine.v1beta.SearchRequest.canonical_filter]
+      // * [SearchRequest.query_expansion_spec][google.cloud.discoveryengine.v1beta.SearchRequest.query_expansion_spec]
+      // * [SearchRequest.spell_correction_spec][google.cloud.discoveryengine.v1beta.SearchRequest.spell_correction_spec]
+      // * [SearchRequest.content_search_spec][google.cloud.discoveryengine.v1beta.SearchRequest.content_search_spec]
+      // * [SearchRequest.user_pseudo_id][google.cloud.discoveryengine.v1beta.SearchRequest.user_pseudo_id]
+      SearchRequest search_request = 2 [(google.api.field_behavior) = REQUIRED];
+    }
+
+    // Required. The specification of the query set.
+    QuerySetSpec query_set_spec = 1 [(google.api.field_behavior) = REQUIRED];
+  }
+
+  // Describes the state of an evaluation.
+  enum State {
+    // The evaluation is unspecified.
+    STATE_UNSPECIFIED = 0;
+
+    // The service is preparing to run the evaluation.
+    PENDING = 1;
+
+    // The evaluation is in progress.
+    RUNNING = 2;
+
+    // The evaluation completed successfully.
+    SUCCEEDED = 3;
+
+    // The evaluation failed.
+    FAILED = 4;
+  }
+
+  // Identifier. The full resource name of the
+  // [Evaluation][google.cloud.discoveryengine.v1beta.Evaluation], in the format
+  // of `projects/{project}/locations/{location}/evaluations/{evaluation}`.
+  //
+  // This field must be a UTF-8 encoded string with a length limit of 1024
+  // characters.
+  string name = 1 [(google.api.field_behavior) = IDENTIFIER];
+
+  // Required. The specification of the evaluation.
+  EvaluationSpec evaluation_spec = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Output only. The metrics produced by the evaluation, averaged across all
+  // [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]s in the
+  // [SampleQuerySet][google.cloud.discoveryengine.v1beta.SampleQuerySet].
+  //
+  // Only populated when the evaluation's state is SUCCEEDED.
+  QualityMetrics quality_metrics = 3
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. The state of the evaluation.
+  State state = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. The error that occurred during evaluation. Only populated when
+  // the evaluation's state is FAILED.
+  google.rpc.Status error = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Timestamp the
+  // [Evaluation][google.cloud.discoveryengine.v1beta.Evaluation] was created
+  // at.
+  google.protobuf.Timestamp create_time = 6
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Timestamp the
+  // [Evaluation][google.cloud.discoveryengine.v1beta.Evaluation] was completed
+  // at.
+  google.protobuf.Timestamp end_time = 7
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. A sample of errors encountered while processing the request.
+  repeated google.rpc.Status error_samples = 8
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+}
+
+// Describes the metrics produced by the evaluation.
+message QualityMetrics {
+  // Stores the metric values at specific top-k levels.
+  message TopkMetrics {
+    // The top-1 value.
+    double top_1 = 1;
+
+    // The top-3 value.
+    double top_3 = 2;
+
+    // The top-5 value.
+    double top_5 = 3;
+
+    // The top-10 value.
+    double top_10 = 4;
+  }
+
+  // Recall per document, at various top-k cutoff levels.
+  //
+  // Recall is the fraction of relevant documents retrieved out of all
+  // relevant documents.
+  //
+  // Example (top-5):
+  //  * For a single
+  //  [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], If 3 out
+  //  of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6
+  TopkMetrics doc_recall = 1;
+
+  // Precision per document, at various top-k cutoff levels.
+  //
+  // Precision is the fraction of retrieved documents that are relevant.
+  //
+  // Example (top-5):
+  //  * For a single
+  //  [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], If 4 out
+  //  of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 =
+  //  0.8
+  TopkMetrics doc_precision = 2;
+
+  // Normalized discounted cumulative gain (NDCG) per document, at various top-k
+  // cutoff levels.
+  //
+  // NDCG measures the ranking quality, giving higher relevance to top
+  // results.
+  //
+  // Example (top-3):
+  //  Suppose [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]
+  //  with three retrieved documents (D1, D2, D3) and binary relevance
+  //  judgements (1 for relevant, 0 for not relevant):
+  //
+  //   Retrieved:  [D3 (0), D1 (1), D2 (1)]
+  //   Ideal:      [D1 (1), D2 (1), D3 (0)]
+  //
+  //   Calculate NDCG@3 for each
+  //   [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]:
+  //    * DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
+  //    * Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
+  //    * NDCG@3: 1.13/1.63 = 0.693
+  TopkMetrics doc_ndcg = 3;
+
+  // Recall per page, at various top-k cutoff levels.
+  //
+  // Recall is the fraction of relevant pages retrieved out of all relevant
+  // pages.
+  //
+  // Example (top-5):
+  //  * For a single
+  //  [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], if 3 out
+  //  of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6
+  TopkMetrics page_recall = 4;
+
+  // Normalized discounted cumulative gain (NDCG) per page, at various top-k
+  // cutoff levels.
+  //
+  // NDCG measures the ranking quality, giving higher relevance to top
+  // results.
+  //
+  // Example (top-3):
+  //  Suppose [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]
+  //  with three retrieved pages (P1, P2, P3) and binary relevance judgements (1
+  //  for relevant, 0 for not relevant):
+  //
+  //   Retrieved:  [P3 (0), P1 (1), P2 (1)]
+  //   Ideal:      [P1 (1), P2 (1), P3 (0)]
+  //
+  //   Calculate NDCG@3 for
+  //   [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]:
+  //    * DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
+  //    * Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
+  //    * NDCG@3: 1.13/1.63 = 0.693
+  TopkMetrics page_ndcg = 5;
+}